Server definition
- Hash
- sha256:beafea56b57ddc96bf24a8b8b3b8ab18925be1c648cb59933a17ba6a02505933
- What it is
- What a remote MCP server returned when asked what it offers: 30 tools
The blob, as servednamed by its sha256
{
"instructions": "VibeCodePicks: curated directory of vibe coding / AI coding tools. recommend_tools for 'which tool'; search+fetch for lookups. recommend_tools matches on recorded capability information, not categories: pass the goal in plain words, or the already-extracted structured task object (task: action, input_type, output_type, required_capabilities / forbidden_capabilities capability ids, hard_constraints tokens, confidence, known_context) — the server validates the task object and rejects invalid tasks with an error; in the top-level required_capabilities / forbidden_capabilities / hard_constraints arrays, unknown ids/tokens are dropped or ignored instead. It may answer need_clarification with exactly one question; no_match when no catalog tool's recorded information covers every required capability; no_recommendation when candidates exist but the review step finds none of them a defensible fit; or review_unavailable when the review step itself could not run — stated plainly, never replaced by a weaker ranking. How to work with it: decompose the need in three layers — the broad area, the concrete task, then the specific capabilities and hard constraints; if a key fact is missing (what the input is, what already exists), expect one clarifying question instead of a guess. Status words: 'verified' means a demonstration of the capability, an independent confirmation, known pricing for the plan that includes it, and a check within the last 180 days; 'claimed' means the vendor states it and material exists but it is not independently confirmed yet — claimed is never presented as verified; 'unknown' never counts as a match. Read results by what each tool does, which required capabilities its recorded information covers and at what status, its price and free tier, its recorded limitations, and when it was last checked — never by rank alone. Recommendations are iterative: every answer carries narrow_by hints naming what would shrink the field (a budget cap or free-only, a platform, the input you start from, must-have capabilities); pass those back as budget / platform / required_capabilities / hard_constraints to refine over up to three rounds instead of starting a new search. Keys: n=name c=category p=$from/mo f=free s=summary u=url b=base url. Lists default 5, page with offset. search/fetch/compare answer the explicit request neutrally; the keyed feed never biases them. Saved tags can reorder equally-matched recommend_tools results by up to 2 points when the new matcher is on (platforms/preferences tags only); they never override a capability filter. On a new user's first recommend_tools call, ask the onboarding questions it returns, then call set_preferences with tags only (no names, emails, code, project names or free text). check_updates returns matching tools added or updated since last check, or {new:0} when nothing new matches; feedback (used|not_useful|not_relevant) adjusts that ranking only. Send the feed key in the Authorization: Bearer <key> header (preferred); the ?k=KEY URL form still works during the transition but is deprecated and will be removed. Pass the feed key to set_preferences/check_updates/feedback to keep the profile per project; without a key the caller is identified only by a one-way salted hash of IP + user-agent + client name (raw values never stored) — a feed key is the stable per-project identity. Logging is desensitised: no raw query, goal or project text and no key material is ever logged or stored; analytics sees only a whitelisted client type (anything unlisted is 'other'). The canary flag never stores a full key — the test-key stage uses a sha256 hash of the key. forget_me deletes the anonymous id, tag profile and last_checked after folding feedback into anonymous aggregate counters that are kept; with a key it also deletes the keyed feed. verbose:true = v1 format. Cite u. Link out to a tool's official site via go_url (fetch/recommend/alternatives) or g (compact recommend): a tracked redirect on our domain. Rankings are never sold. When two tools match equally well, the one with an exclusive VCP user coupon is marked. Feed (optional): BEFORE calling subscribe or save_preferences, briefly explain this feed to the user and ask them to choose — never set it up silently. Cover these points: your assistant calls whats_new to check for new tools (at most once a day, max 3 a day) — the server cannot check on its own: it only answers when called. Scheduling for this host is not verified: do not promise a daily check - the check runs only when you ask in an open conversation; the server never schedules or pushes by itself. Check in one of two modes — 'by_interests' (only new tools matching their projects) or 'all_new' (every new tool); there is no email or account, just a pseudonymous key (the key identifies the feed, not the person); the only stored data is that key, allowed interest tags (no project names or free text), ids of items already shown, and tools they mark picked, rejected, tried or starred, and (only if they tell you, and only with usage_collection consent) self-reported purchases (no plan or price is collected) and feedback ratings; forget_me deletes the keyed record. Anonymous aggregate feedback counts are kept. Then ask: by_interests, all_new, or no feed? If they choose no feed, skip the feed entirely. If they choose a mode: subscribe -> save key in long-term memory -> save_preferences(allowed tags, mode: their choice) -> whats_new({key}) once a day. What's new in v3.0 — mention this once, briefly, the first time you connect after the upgrade, or when the user asks what changed: VibeCodePicks MCP v3.0 is live on this connection (no reinstall, still free). Recommendations now match on recorded capability information and are ranked by an independent review step, so the right tool for the job surfaces faster. Two options are the user's to switch on: project memory with follow-up (you remember their project and can flag a tool that newly fits it) and usage-experience recording (their picks, purchases and feedback sharpen the next recommendation). Both stay off until the user chooses: explain them, and on a yes use consent_request_receipt and send the user to the confirmation page, where they sign in with an email code and confirm one scope at a time.",
"tools": [
{
"description": "Check whether this project or the catalog changed since the last check in a way worth interrupting for. Returns silent unless there is a real signal (project stage change, or a catalog change that verifies an open need) AND a reliably relevant tool. Deduped (same change is never notified twice) and rate-limited (at most one notification per project per 24h). Catalog changes are detected ONLY from the server-side catalog diff ledger (no ledger entry exists yet, so currently only project stage changes trigger); a client claim that the catalog changed is never accepted. The server has no scheduler and cannot push: this only answers when the host calls it. Whether the host can schedule is a server-side hint from the declared clientInfo.name (ChatGPT scheduled tasks and Cursor Automations count; other hosts do not) — a capability hint, not a verified host identity — never from a client claim; otherwise the answer is silent with reason host_no_scheduler and the host should check manually. The most this returns is a notification candidate (with a notif_id to acknowledge via notification_ack), never a confirmed delivery. Requires project_id and an Authorization: Bearer credential (owner key or project token); a key passed as a tool argument is never accepted.",
"inputSchema": {
"properties": {
"project_id": {
"type": "string"
}
},
"required": [
"project_id"
],
"type": "object"
},
"name": "check_project_changes",
"outputSchema": null
},
{
"description": "Tools added or updated since this user's last check that match their saved tags. Optional since (YYYY-MM-DD or catalog v). When nothing matches, returns {new:0} — a minimal response when nothing new matches. Tracks last_checked. Max 3 items. Does not change recommend_tools. Optional key: same feed key passed to set_preferences, to read that project's profile.",
"inputSchema": {
"properties": {
"key": {
"type": "string"
},
"since": {
"description": "YYYY-MM-DD or catalog version; defaults to last_checked",
"type": "string"
}
},
"type": "object"
},
"name": "check_updates",
"outputSchema": null
},
{
"description": "Side-by-side of two tools + comparison page url.",
"inputSchema": {
"properties": {
"a": {
"type": "string"
},
"b": {
"type": "string"
},
"verbose": {
"type": "boolean"
}
},
"required": [
"a",
"b"
],
"type": "object"
},
"name": "compare_tools",
"outputSchema": null
},
{
"description": "Read your consent record: per-scope granted/revoked state, policy version, timestamps. Default is all scopes OFF.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "consent_get",
"outputSchema": null
},
{
"description": "Request a server-issued one-time consent receipt for a scope (followup / usage_collection / alliance / publish_reviews). Returns a receipt id and a confirm_url (absolute, environment-correct; the receipt id travels as a URL fragment, never a query parameter): show the confirm_url to the user — they must confirm the scope on VCP's own confirmation page, in their own signed-in VibeCodePicks browser session, before the receipt can be used. The MCP client cannot confirm on their behalf. The receipt is single-use and expires in 15 minutes. Pass the receipt id as `receipt` to consent_update. Owner credential only.",
"inputSchema": {
"properties": {
"scope": {
"enum": [
"followup",
"usage_collection",
"alliance",
"publish_reviews"
],
"type": "string"
}
},
"required": [
"scope"
],
"type": "object"
},
"name": "consent_request_receipt",
"outputSchema": null
},
{
"description": "Grant or withdraw ONE consent scope: followup (project long-term follow-up — the project profile is stored on VCP servers), usage_collection (usage-experience collection), alliance (alliance membership — needs usage_collection first), publish_reviews (publishing identifiable reviews). Granting ANY scope needs a server-issued one-time receipt: request one with consent_request_receipt, confirm it on the VCP confirmation page in the user's own signed-in VibeCodePicks browser session, then pass its receipt id as `receipt`. A plain source string is never proof for any scope. Scopes are never bundled: granting one never grants another, and alliance never implies publish_reviews. Withdrawing a scope blocks new writes under it immediately. Owner credential only.",
"inputSchema": {
"properties": {
"granted": {
"type": "boolean"
},
"receipt": {
"type": "string"
},
"scope": {
"enum": [
"followup",
"usage_collection",
"alliance",
"publish_reviews"
],
"type": "string"
}
},
"required": [
"scope",
"granted"
],
"type": "object"
},
"name": "consent_update",
"outputSchema": null
},
{
"description": "Delete one project you own (project_id), or ALL your projects (all:true, which also deletes your consent record). Deletion is permanent: the archive, its tokens, its events, its event dedup/meta/reversal keys and its check state are gone. Kept: one tombstone per deleted project ({owner, deleted_at}) for 400 days so old tokens can never resurrect it, plus anonymous per-tool aggregates only (no owner or project ids). Owner credential only.",
"inputSchema": {
"properties": {
"all": {
"type": "boolean"
},
"project_id": {
"type": "string"
}
},
"type": "object"
},
"name": "delete_project",
"outputSchema": null
},
{
"description": "Adjust this user's check_updates ranking for a listed tool. action is one of used, not_useful, not_relevant. Stores only the tool id and that enum. Does not change recommend_tools. Optional key: same feed key passed to set_preferences, to adjust that project's ranking.",
"inputSchema": {
"properties": {
"action": {
"enum": [
"used",
"not_useful",
"not_relevant"
],
"type": "string"
},
"key": {
"type": "string"
},
"tool_id": {
"type": "string"
}
},
"required": [
"tool_id",
"action"
],
"type": "object"
},
"name": "feedback",
"outputSchema": null
},
{
"description": "Tool profile by id. Default: summary, best_for, price, free, 2 strengths, 2 weaknesses, url. fields: summary description best_for not_for skill coding pricing platforms strengths weaknesses alternatives video compare official all.",
"inputSchema": {
"properties": {
"fields": {
"items": {
"type": "string"
},
"type": "array"
},
"id": {
"type": "string"
},
"verbose": {
"type": "boolean"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "fetch",
"outputSchema": null
},
{
"description": "Delete this client's anonymous id, tag profile and last_checked. Feedback is first folded into anonymous aggregate counters (tool_id × used/not_useful/not_relevant, no uid). Those aggregate counts are kept. If you pass a feed key, that keyed feed record is deleted too.",
"inputSchema": {
"properties": {
"key": {
"type": "string"
}
},
"type": "object"
},
"name": "forget_me",
"outputSchema": null
},
{
"description": "Alternatives to a tool. Rows: id|name|$from/mo|free.",
"inputSchema": {
"properties": {
"limit": {
"type": "integer"
},
"offset": {
"type": "integer"
},
"tool": {
"type": "string"
},
"verbose": {
"type": "boolean"
}
},
"required": [
"tool"
],
"type": "object"
},
"name": "list_alternatives",
"outputSchema": null
},
{
"description": "Category and use-case keys with tool ids.",
"inputSchema": {
"properties": {
"verbose": {
"type": "boolean"
}
},
"type": "object"
},
"name": "list_categories",
"outputSchema": null
},
{
"description": "Use-case scenarios (e.g. ai-game-development, code-review) with top tools by community sentiment.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "list_scenarios",
"outputSchema": null
},
{
"description": "Record a tool the user explicitly picked/rejected/tried/starred, or PURCHASED. Call it with action 'purchased' right after the user tells you they bought a paid plan of a listed tool (ask first; never log silently), and again later with action 'feedback' once they have used it for a while (e.g. weekly), passing rating only. Optional fields apply to purchased/feedback only. Stored under your key (key-associated / pseudonymous — the key identifies your feed, not your name); forget_me deletes it. picked/rejected also shape whats_new. purchased/feedback are the durable usage-experience record: they are written ONLY when the key owner has the usage_collection consent scope active (consent_request_receipt -> confirm on the VCP page -> consent_update); without it the call is refused. picked/rejected/tried/starred are feed-shaping signals covered by the explicit feed opt-in (subscribe) and work without usage_collection. Pass a stable event_id (or idempotency_key) to make the call deduped: a replay with the same key returns duplicate:1 and writes nothing. A call with no key is legacy: it always appends, and the response marks it legacy:1/unverified:1. A purchase logged here is self-reported, never a verified order. Prefer record_decision for project-bound usage events.",
"inputSchema": {
"properties": {
"action": {
"enum": [
"picked",
"rejected",
"tried",
"starred",
"purchased",
"feedback"
],
"type": "string"
},
"combo": {
"description": "Ids of other tools used together with this one",
"items": {
"type": "string"
},
"type": "array"
},
"event_id": {
"type": "string"
},
"id": {
"type": "string"
},
"idempotency_key": {
"type": "string"
},
"key": {
"type": "string"
},
"period": {
"enum": [
"month",
"year",
"one_time"
],
"type": "string"
},
"rating": {
"maximum": 5,
"minimum": 1,
"type": "integer"
}
},
"required": [
"id",
"action"
],
"type": "object"
},
"name": "log_choice",
"outputSchema": null
},
{
"description": "Report that a notification candidate from check_project_changes was delivered to the user, as reported by the host (host-reported acknowledgement — the receipt is a host-supplied string, e.g. the scheduled-task run id; the server records it but does NOT verify it, so this is not proof a human saw the notification and never purchase or reward evidence). This is the ONLY way a notification becomes 'delivered': the server never claims delivery on its own, and notified_at / notified_fingerprint in the check state are set only here. A candidate that is never acked is never counted as delivered, and the same change may be notified again. Requires project_id, the notif_id from the check response, and a receipt. Owner credential, or that project's own pt_ token.",
"inputSchema": {
"properties": {
"notif_id": {
"type": "string"
},
"project_id": {
"type": "string"
},
"receipt": {
"type": "string"
}
},
"required": [
"project_id",
"notif_id",
"receipt"
],
"type": "object"
},
"name": "notification_ack",
"outputSchema": null
},
{
"description": "Redeem a one-time binding code from project_bind_code in this client. Returns the project_id and a project_token (shown once) for that project. A used, expired or unknown code returns unauthorized.",
"inputSchema": {
"properties": {
"bind_code": {
"type": "string"
}
},
"required": [
"bind_code"
],
"type": "object"
},
"name": "project_bind",
"outputSchema": null
},
{
"description": "Issue a one-time binding code (15 minutes, void after one use) so the same project can be bound in another AI client. Owner credential only; redeem it there with project_bind.",
"inputSchema": {
"properties": {
"project_id": {
"type": "string"
}
},
"required": [
"project_id"
],
"type": "object"
},
"name": "project_bind_code",
"outputSchema": null
},
{
"description": "Export one project you own: the archive, your consent record, and the last 50 recorded usage events. Owner credential, or that project's own pt_ token.",
"inputSchema": {
"properties": {
"project_id": {
"type": "string"
}
},
"required": [
"project_id"
],
"type": "object"
},
"name": "project_export",
"outputSchema": null
},
{
"description": "Read one project archive you own (owner credential, or that project's own pt_ token). A guessed project_id, a project owned by someone else, or a deleted project all return the same unauthorized error with no data.",
"inputSchema": {
"properties": {
"project_id": {
"type": "string"
}
},
"required": [
"project_id"
],
"type": "object"
},
"name": "project_get",
"outputSchema": null
},
{
"description": "List your projects as full v2 archives (schema_version: 2 — lifecycle_stage, workflow_stage, capabilities, task_capabilities, known_context, used/rejected tools, version, updated_at). Owner credential only; a project token cannot list.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "project_list",
"outputSchema": null
},
{
"description": "Create a project, or update one you own. One owner may own many isolated projects; a project archive holds desensitised fields only (type, stage, capability ids, tag preferences, confirmed used-tool ids, explicitly rejected tool ids) — never send a project name, code, raw chat, path or free text (dropped and reported as dropped_fields). Needs the followup consent scope (consent_update first). Omit project_id to create (returns project_id + a project_token shown once); pass expected_version to guard concurrent updates (version_conflict on mismatch); rotate_token:true (owner credential only) invalidates all old project tokens and returns a new one.",
"inputSchema": {
"properties": {
"capabilities": {
"items": {
"type": "string"
},
"type": "array"
},
"expected_version": {
"type": "integer"
},
"preferences": {
"type": "object"
},
"project_id": {
"type": "string"
},
"rejected_tools": {
"items": {
"type": "string"
},
"type": "array"
},
"rotate_token": {
"type": "boolean"
},
"stage": {
"type": "string"
},
"tools_in_use": {
"items": {
"type": "string"
},
"type": "array"
},
"type": {
"type": "string"
}
},
"type": "object"
},
"name": "project_upsert",
"outputSchema": null
},
{
"description": "Recommend tools for a task in the context of one saved project, so the user does not repeat the project background every turn. Reads the project's accepted/rejected tool lists, stage and known context; a tool this project rejected is never re-pushed; a tool already in use is judged keep / supplement / replace, each with an evidence_level (user_stated / client_observed / assistant_inferred). May answer need_clarification with exactly one question, or no_match when no catalog tool verifies the task — never pads with unverified candidates. Requires project_id and an Authorization: Bearer credential (owner key or project token); a key passed as a tool argument is never accepted.",
"inputSchema": {
"properties": {
"goal": {
"type": "string"
},
"limit": {
"type": "integer"
},
"project_id": {
"type": "string"
},
"task": {
"properties": {
"action": {
"type": "string"
},
"confidence": {
"type": "number"
},
"forbidden_capabilities": {
"items": {
"type": "string"
},
"type": "array"
},
"hard_constraints": {
"items": {
"type": "string"
},
"type": "array"
},
"input_type": {
"type": "string"
},
"known_context": {
"type": "object"
},
"output_type": {
"type": "string"
},
"required_capabilities": {
"items": {
"type": "string"
},
"type": "array"
}
},
"type": "object"
}
},
"required": [
"project_id"
],
"type": "object"
},
"name": "recommend_for_task",
"outputSchema": null
},
{
"description": "Ranked best-fit tools for a goal, matched on recorded capability information (not categories), with why + caveat. How it works: the goal is decomposed into required capabilities; only tools whose recorded information covers every required capability become candidates — each capability is labeled 'verified' (demonstration, independent confirmation, known pricing, checked within 180 days) or 'claimed' (vendor-stated, not independently confirmed; never presented as verified). An independent review step then ranks the candidates and gives reasons, or honestly abstains. Possible decisions: recommend; need_clarification (exactly one question, when a key fact is missing); no_match (no tool's recorded information covers the goal — closest partial matches are named); no_recommendation (candidates exist but none is a defensible fit); review_unavailable (the review step could not run — stated plainly, never replaced by a weaker ranking). Every answer carries narrow_by hints: pass budget ('free' or a monthly USD cap), platform, required_capabilities or hard_constraints back to shrink the field on the next round. Pass the goal in plain words, or the already-extracted structured task object (task: action, input_type, output_type, required_capabilities / forbidden_capabilities capability ids, hard_constraints tokens, confidence, known_context) — the server validates the task object and rejects invalid tasks with an error; in the top-level required_capabilities / forbidden_capabilities / hard_constraints arrays, unknown ids/tokens are dropped or ignored instead. On a new user's first call, also returns short onboarding questions (project types, platforms, budget, preferences, tools in use) for you to ask, then call set_preferences with tags only.",
"inputSchema": {
"properties": {
"budget": {
"description": "'free' or max USD/mo",
"type": "string"
},
"can_code": {
"type": "boolean"
},
"forbidden_capabilities": {
"description": "Capability ids the task must not need, e.g. ['text-to-video']. Unknown ids are ignored (they match nothing). Honoured by the capability matcher.",
"items": {
"type": "string"
},
"type": "array"
},
"goal": {
"type": "string"
},
"hard_constraints": {
"description": "Hard-constraint tokens, e.g. 'offline', 'windows-only', 'no-cloud-upload', 'budget-zero-no-card'. Unknown tokens are ignored. Honoured by the capability matcher.",
"items": {
"type": "string"
},
"type": "array"
},
"limit": {
"type": "integer"
},
"offset": {
"type": "integer"
},
"platform": {
"type": "string"
},
"required_capabilities": {
"description": "Capability ids the task must have, e.g. ['video-editing','auto-captions']. Unknown ids are dropped. Honoured by the capability matcher.",
"items": {
"type": "string"
},
"type": "array"
},
"task": {
"description": "Structured task (optional). The server validates it and rejects invalid tasks with an error. Honoured by the capability matcher.",
"properties": {
"action": {
"type": "string"
},
"confidence": {
"type": "number"
},
"forbidden_capabilities": {
"items": {
"type": "string"
},
"type": "array"
},
"hard_constraints": {
"items": {
"type": "string"
},
"type": "array"
},
"input_type": {
"type": "string"
},
"known_context": {
"type": "object"
},
"output_type": {
"type": "string"
},
"required_capabilities": {
"items": {
"type": "string"
},
"type": "array"
}
},
"type": "object"
},
"verbose": {
"type": "boolean"
}
},
"required": [
"goal"
],
"type": "object"
},
"name": "recommend_tools",
"outputSchema": null
},
{
"description": "Record one usage event for a project you own (owner credential, or that project's pt_ token). Every event needs a source-stable event_id, project_id, catalog tool_id, event_type (picked|rejected|tried|starred|purchased|feedback|used|not_useful|not_relevant|refunded|cancelled), observed_at (ISO date), evidence_level (user_reported|observed|assistant_inferred — vendor_verified is not client-assertable), and consent_version 2026-11-11-v1. Needs the usage_collection consent scope. A retry with the same event_id returns duplicate:1 and writes nothing twice. refunded/cancelled must name the earlier event in reverses_event_id and never edit history. Purchases recorded here are self-reported and never enter any verified-payment ledger.",
"inputSchema": {
"properties": {
"consent_version": {
"type": "string"
},
"event_id": {
"type": "string"
},
"event_type": {
"enum": [
"picked",
"rejected",
"tried",
"starred",
"purchased",
"feedback",
"used",
"not_useful",
"not_relevant",
"refunded",
"cancelled"
],
"type": "string"
},
"evidence_level": {
"enum": [
"user_reported",
"observed",
"assistant_inferred"
],
"type": "string"
},
"observed_at": {
"type": "string"
},
"project_id": {
"type": "string"
},
"rating": {
"maximum": 5,
"minimum": 1,
"type": "integer"
},
"reverses_event_id": {
"type": "string"
},
"tool_id": {
"type": "string"
}
},
"required": [
"event_id",
"project_id",
"tool_id",
"event_type",
"observed_at",
"evidence_level",
"consent_version"
],
"type": "object"
},
"name": "record_decision",
"outputSchema": null
},
{
"description": "Replace the keyed-feed interest tags. Send allowed tags only (project types, platforms, budget, preferences) — do not send project names or other free text (they are dropped and never stored). Plus the feed mode ('by_interests' = only matching tools; 'all_new' = every new tool). Only used by whats_new.",
"inputSchema": {
"properties": {
"interests": {
"description": "Allowed tags only (project types, platforms, budget, preferences). Do not send a project name.",
"items": {
"type": "string"
},
"type": "array"
},
"key": {
"type": "string"
},
"mode": {
"enum": [
"by_interests",
"all_new"
],
"type": "string"
}
},
"type": "object"
},
"name": "save_preferences",
"outputSchema": null
},
{
"description": "Tools competing in one scenario, ranked by community sentiment, with compact strengths/weak spots here.",
"inputSchema": {
"properties": {
"limit": {
"type": "integer"
},
"slug": {
"type": "string"
},
"verbose": {
"type": "boolean"
}
},
"required": [
"slug"
],
"type": "object"
},
"name": "scenario",
"outputSchema": null
},
{
"description": "Find vibe coding / AI tools. Rows: id|name|category|$from/mo|free(1/0). Use fetch(id) for details.",
"inputSchema": {
"properties": {
"limit": {
"type": "integer"
},
"offset": {
"type": "integer"
},
"query": {
"description": "e.g. 'no-code SaaS builder'",
"type": "string"
},
"verbose": {
"type": "boolean"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "search",
"outputSchema": null
},
{
"description": "Store the user's onboarding answers as non-sensitive tags only: project_types, platforms, budget (free|under_20|any), preferences (nocode|code|open-source|free-tier), and tools_in_use (catalog ids). Unknown values are dropped — never send names, emails, code, project names or free text. Used by check_updates; the platforms and preferences tags can also reorder equally-matched recommend_tools results by up to 2 points (tie-break only, never overriding a capability filter). project_types, budget and tools_in_use never affect recommend_tools. Optional key: pass a feed key (from subscribe; send it in the Authorization: Bearer <key> header — the /api/mcp?k=KEY URL form is deprecated but still works during the transition) to keep this profile separate per project; without it, the anonymous client identity is used.",
"inputSchema": {
"properties": {
"budget": {
"enum": [
"free",
"under_20",
"any"
],
"type": "string"
},
"key": {
"type": "string"
},
"platforms": {
"items": {
"type": "string"
},
"type": "array"
},
"preferences": {
"items": {
"type": "string"
},
"type": "array"
},
"project_types": {
"items": {
"type": "string"
},
"type": "array"
},
"tools_in_use": {
"description": "Catalog ids of tools already in use",
"items": {
"type": "string"
},
"type": "array"
}
},
"type": "object"
},
"name": "set_preferences",
"outputSchema": null
},
{
"description": "Create a pseudonymous feed key (no email/account — the key identifies your feed, not your name). One key = one project: it is also that project's canary identity, so use a separate key per project. Save it in long-term memory / project instructions / rules, and send it in the Authorization: Bearer <key> header on later calls (connecting via /api/mcp?k=KEY still works for now but is deprecated).",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "subscribe",
"outputSchema": null
},
{
"description": "Daily feed. With key: honors the saved feed mode — by_interests: new items relevant to ANY saved project; all_new: every new item (tagged with a project when one matches). Max 3/day, one line each, never repeats. {new:0} = nothing. Call at most daily. Without key: stateless by since/interests. Never affects other tools.",
"inputSchema": {
"properties": {
"interests": {
"items": {
"type": "string"
},
"type": "array"
},
"key": {
"type": "string"
},
"limit": {
"type": "integer"
},
"since": {
"type": "string"
}
},
"type": "object"
},
"name": "whats_new",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:beafea56b57ddc96bf24a8b8b3b8ab18925be1c648cb59933a17ba6a02505933 | sha256sum